Ph.D. Candidate at SNU Computer Vision Lab
CONTHO_RELEASE. [CVPR 2024] This repo is official PyTorch implementation of Joint Reconstruction of 3D Human and Object via Contact-Based Refinement Transformer.
112HACO_RELEASE. [NeurIPS 2025] This repo is official PyTorch implementation of the paper "Learning Dense Hand Contact Estimation from Imbalanced Data".
62Egyptian_Hieroglyph_Classification_ConvNet. A PyTorch implementation of the paper "A Deep Learning Approach to Ancient Egyptian Hieroglyphs Classification" by Barucci et al.
5ViT-PyTorch. Implementation for CIFAR-10 challenge with Vision Transformer Model (compared with CNN based Models) from scratch
3Wonder3D. Single Image to 3D using Cross-Domain Diffusion for 3D Generation
2LION. Latent Point Diffusion Models for 3D Shape Generation
2Lawyers_Twitter_Turnover. A BeautifulSoup4 (Python library), Tweepy (Python library) implementation for web scraping the lawfirm webpages
2ViT-PyTorch-Lightning. Implementation for CIFAR-10 challenge with Vision Transformer Model (compared with CNN based Models) on PyTorch Lightning
2mesh-fusion. Python tool for obtaining watertight meshes using TSDF fusion.
2dqj5182.
2deco. Estimate vertex-level 3D human-scene and human-object contacts across the full body mesh
1awesome-science-aiml-papers. AI, ML papers published at Science
13dgs-mcmc. [NeurIPS 2024 Spotlight] Implementation of the paper "3D Gaussian Splatting as Markov Chain Monte Carlo"
1hamer-1. HaMeR: Reconstructing Hands in 3D with Transformers
1fix_shapenet_mesh. Python
1CLOSER_ECCV2024. Python
1loss-landscape. Code for visualizing the loss landscape of neural nets
1awesome-nature-aiml-papers. AI, ML papers published at Nature
1WHAM-1. Python
1dqj5182.github.io. CSS
1grokfast. Official repository for the paper "Grokfast: Accelerated Grokking by Amplifying Slow Gradients"
1gmflow. [CVPR'22 Oral] GMFlow: Learning Optical Flow via Global Matching
1DeepSDF. Learning Continuous Signed Distance Functions for Shape Representation
1Michelangelo. [NeurIPS 2023] Michelangelo: Conditional 3D Shape Generation based on Shape-Image-Text Aligned Latent Representation
1affordance_diffusion. Codes for "Affordance Diffusion: Synthesizing Hand-Object Interactions"
1DexGraspNet. Python
1Image-Harmonization-Dataset-iHarmony4. [CVPR 2020] The first large-scale public benchmark dataset for image harmonization. The code used in our paper "DoveNet: Deep Image Harmonization via Domain Verification", CVPR2020. Useful for image harmonization, image composition, etc.
1gSDF. gSDF: Geometry-Driven Signed Distance Functions for 3D Hand-Object Reconstruction, CVPR 2023.
1setvae. [CVPR'21] SetVAE: Learning Hierarchical Composition for Generative Modeling of Set-Structured Data, in PyTorch
1contactgen. ContactGen: Generative Contact Modeling for Grasp Generation (ICCV 2023)
1TeSTra. Code for ECCV2022 "Real-time Online Video Detection with Temporal Smoothing Transformers"
1AlignSDF. AlignSDF: Pose-Aligned Signed Distance Fields for Hand-Object Reconstruction, ECCV 2022
1AlphaPose. Real-Time and Accurate Full-Body Multi-Person Pose Estimation&Tracking System
1Manifold. Convert any Triangle Mesh to Watertight Manifold
1ControlNet. Let us control diffusion models!
1Paint3D. Paint3D: Paint Anything 3D with Lighting-Less Texture Diffusion Models, a no lighting baked texture generative model
1lensing-neural-fields. Implicit neural representations for strong lensing source reconstruction. Code repository associated with https://arxiv.org/abs/2206.14820.
1StreamMultiDiffusion. Official code for the paper "StreamMultiDiffusion: Real-Time Interactive Generation with Region-Based Semantic Control."
1Pose2Mesh_RELEASE. Official Pytorch implementation of "Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Pose", ECCV 2020
1s2am. [TIP 2020] Improving the Harmony of the Composite Image by Spatial-Separated Attention Module
1pyskl. A toolbox for skeleton-based action recognition.
1Diffusion-SDF. [CVPR 2023] Diffusion-SDF: Text-to-Shape via Voxelized Diffusion
1ihoi. Python
1Clip-Forge. Python
1mesh_to_sdf. Calculate signed distance fields for arbitrary meshes
1SPIN. Repository for the paper "Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loop"
1PoseFormerV2. The project is an official implementation of our paper "PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose Estimation".
1dqj5182_edit.github.io. CSS
1dqj5182_old.github.io. Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes
1download_finegym. Python
1pedestrian-detection-and-segmentation. Jupyter Notebook
1Weighted_Random_Sampling_for_Egyptian_Hieroglyph_Classification. A Pytorch implementation of "Egyptian hieroglpyh classification using Capsule Network" by Daniel Jung, Kangdong Yuan, and Kaamran Raahemifar
1Predict_Annual_Performance_Individual_Stocks_Clustering_Method. A scikit-learn implementation of predicting annual performance of individual stocks using Decision Tree, KNN, Regression method
1Sparse_COO_Tensor_Multiplication_Pytorch. Pytorch Sparse COO Tensor Multiplication
1Weight_Initialization_Method_using_Monte_Carlo_Simulation. Jupyter Notebook
1